Self-supervised graph representation learning has recently shown considerable promise in a range of fields, including bioinformatics and social networks. A large number of graph contrastive learning approaches have shown promising performance for representation learning on graphs, which train models by maximizing agreement between original graphs and their augmented views (i.e., positive views). Unfortunately, these methods usually involve pre-defined augmentation strategies based on the knowledge of human experts. Moreover, these strategies may fail to generate challenging positive views to provide sufficient supervision signals. In this paper, we present a novel approach named Graph Pooling ContraSt (GPS) to address these issues. Motivated by the fact that graph pooling can adaptively coarsen the graph with the removal of redundancy, we rethink graph pooling and leverage it to automatically generate multi-scale positive views with varying emphasis on providing challenging positives and preserving semantics, i.e., strongly-augmented view and weakly-augmented view. Then, we incorporate both views into a joint contrastive learning framework with similarity learning and consistency learning, where our pooling module is adversarially trained with respect to the encoder for adversarial robustness. Experiments on twelve datasets on both graph classification and transfer learning tasks verify the superiority of the proposed method over its counterparts.

翻译：自监督图表示学习近年来在生物信息学、社交网络等领域展现出显著潜力。大量图对比学习方法通过最大化原始图与其增强视图（即正视图）的一致性来训练模型，在图的表示学习上取得了优异性能。然而，这些方法通常依赖基于专家知识预定义的增强策略，且此类策略可能无法生成具有挑战性的正视图以提供充分的监督信号。本文提出一种名为图池化对比学习（GPS）的新方法来解决这些问题。受图池化能通过去除冗余自适应粗化图的启发，我们重新审视图池化并利用其自动生成多尺度正视图——强增强视图与弱增强视图——在提供挑战性正例与保留语义之间实现差异化侧重。随后，我们将两种视图融入包含相似性学习和一致性学习的联合对比学习框架，并对编码器进行池化模块的对抗训练以提升鲁棒性。在十二个数据集上的图分类与迁移学习实验验证了所提方法相较同类方法的优越性。